Agent-assisted product initiatives · MIT · on npm

Run a product initiative,
end to end.

Blueprint is a methodology and CLI for running product work with an AI agent. You bring the context — screenshots, BRDs, codebase, competitive intel. The agent runs the pipeline and ships one portal that serves leadership, engineering, and everyone.

$ npx @nino-chavez-labs/blueprint-cli init
Quickstart ↓ npm ↗ github ↗

One pipeline. Seven stages.

Each stage produces artifacts that feed the next. The insight: prototype and documents are built simultaneously — the prototype tests the decision, the docs capture the rationale.

  1. 01 Research

    competitive analysis, codebase, comparables

  2. 02 Design

    codify what the prototype can and cannot do

  3. 03 Prototype

    HTML pages matching the real product

  4. 04 Fact-check

    every claim validated against source

  5. 05 Document

    strategy, feasibility, integration plans

  6. 06 Deploy

    one portal — docs + prototype + chat

  7. 07 Iterate

    stakeholder feedback, triaged

This site is Blueprint output.

Every page here was generated from a single blueprint.yml by the same pipeline you’d run. The CLI is live on npm; the portal deploys from one config. Blueprint is its own first consumer — the methodology used to productize the methodology.

10ADRs
6CLI commands
1config → whole portal
explore it →

Up and running in five steps.

Copy, paste, go. No decisions to make first.

  1. 1

    Prerequisites

    Node 18+ and Claude Code. That’s it — there’s no server to stand up and nothing to host.

  2. 2

    Scaffold your initiative

    Stamps a portal you own, validated against the variant × tier matrix.

    $ npx @nino-chavez-labs/blueprint-cli init --pattern=A --target=my-initiative
  3. 3

    Configure

    Set the three things that matter in blueprint.yml — the rest has sane defaults.

    variant: brownfield   # greenfield | midstream | brownfield
tier: 1               # deliverable sophistication 0–2
portal_pattern: A     # A = platform portal · B = redesign review
  4. 4

    Run the pipeline

    In Claude Code, the stages are skills. Run them in order — each gate is enforced by a reviewer.

    /blueprint-research → /blueprint-prototype → /blueprint-docs → /blueprint-validate → /blueprint-deploy
  5. 5

    Ship & check

    Push and your portal deploys. Verify conformance — doctor is honest about what it didn’t check.

    $ npx @nino-chavez-labs/blueprint-cli doctor

The CLI

Six commands, all real. npx @nino-chavez-labs/blueprint-cli <command> — zero install.

blueprint init

Scaffold a new initiative and its portal — validated against the variant × tier matrix.

blueprint review

Run an executable stage-gate reviewer. --list shows canonical + org-authored ones.

blueprint cost

Per-stage effort/model configuration and telemetry — dial spend up or down.

blueprint fleet

Classify every consumer’s drift from the methodology, from one registry.

blueprint upgrade

Bump a consumer’s methodology pin — terraform-style, dry-run by default.

blueprint doctor

Conformance + health: loads the config, every reviewer, and portal checks.

Stay current. Feed back upstream.

Updates flow down without breaking you; your fixes and gaps flow back up.

Pull updates

blueprint upgrade reads your methodology pin, shows the delta, and bumps it — non-breaking, dry-run by default. blueprint fleet shows drift across every initiative.

$ npx @nino-chavez-labs/blueprint-cli upgrade

Report & request upstream

Hit a gap, a bug, or a feature need? File an amendment or RFC. The 4-bucket triage routes it automatically — substantial change → RFC first, bug-fix → straight PR.

How to contribute →

Go deeper

Methodology

The first principles, the seven stages, the variant ladder.

Decisions

10 architecture decision records — the why behind every primitive.

The live portal

Discover · Try · Build · Operate · Inspect · Roadmap — the deeper reference.

Source on GitHub

The methodology, the CLI, the template, the reviewer set.